Examples with GroupCombineOperatorBase org.apache.flink.api.common.operators.base.GroupCombineOperatorBase used on opensource projects

Example 1 with GroupCombineOperatorBase

use of org.apache.flink.api.common.operators.base.GroupCombineOperatorBase in project flink by apache.

the class GroupCombineOperator method translateToDataFlow.

// --------------------------------------------------------------------------------------------
//  Translation
// --------------------------------------------------------------------------------------------
@Override
protected GroupCombineOperatorBase<?, OUT, ?> translateToDataFlow(Operator<IN> input) {
    String name = getName() != null ? getName() : "GroupCombine at " + defaultName;
    // distinguish between grouped reduce and non-grouped reduce
    if (grouper == null) {
        // non grouped reduce
        UnaryOperatorInformation<IN, OUT> operatorInfo = new UnaryOperatorInformation<>(getInputType(), getResultType());
        GroupCombineOperatorBase<IN, OUT, GroupCombineFunction<IN, OUT>> po = new GroupCombineOperatorBase<>(function, operatorInfo, new int[0], name);
        po.setInput(input);
        // the parallelism for a non grouped reduce can only be 1
        po.setParallelism(1);
        return po;
    }
    if (grouper.getKeys() instanceof SelectorFunctionKeys) {
        @SuppressWarnings("unchecked") SelectorFunctionKeys<IN, ?> selectorKeys = (SelectorFunctionKeys<IN, ?>) grouper.getKeys();
        if (grouper instanceof SortedGrouping) {
            SortedGrouping<IN> sortedGrouping = (SortedGrouping<IN>) grouper;
            SelectorFunctionKeys<IN, ?> sortKeys = sortedGrouping.getSortSelectionFunctionKey();
            Ordering groupOrder = sortedGrouping.getGroupOrdering();
            PlanUnwrappingSortedGroupCombineOperator<IN, OUT, ?, ?> po = translateSelectorFunctionSortedReducer(selectorKeys, sortKeys, groupOrder, function, getResultType(), name, input);
            po.setParallelism(this.getParallelism());
            return po;
        } else {
            PlanUnwrappingGroupCombineOperator<IN, OUT, ?> po = translateSelectorFunctionReducer(selectorKeys, function, getResultType(), name, input);
            po.setParallelism(this.getParallelism());
            return po;
        }
    } else if (grouper.getKeys() instanceof Keys.ExpressionKeys) {
        int[] logicalKeyPositions = grouper.getKeys().computeLogicalKeyPositions();
        UnaryOperatorInformation<IN, OUT> operatorInfo = new UnaryOperatorInformation<>(getInputType(), getResultType());
        GroupCombineOperatorBase<IN, OUT, GroupCombineFunction<IN, OUT>> po = new GroupCombineOperatorBase<>(function, operatorInfo, logicalKeyPositions, name);
        po.setInput(input);
        po.setParallelism(getParallelism());
        // set group order
        if (grouper instanceof SortedGrouping) {
            SortedGrouping<IN> sortedGrouper = (SortedGrouping<IN>) grouper;
            int[] sortKeyPositions = sortedGrouper.getGroupSortKeyPositions();
            Order[] sortOrders = sortedGrouper.getGroupSortOrders();
            Ordering o = new Ordering();
            for (int i = 0; i < sortKeyPositions.length; i++) {
                o.appendOrdering(sortKeyPositions[i], null, sortOrders[i]);
            }
            po.setGroupOrder(o);
        }
        return po;
    } else {
        throw new UnsupportedOperationException("Unrecognized key type.");
    }
}

Example 2 with GroupCombineOperatorBase

use of org.apache.flink.api.common.operators.base.GroupCombineOperatorBase in project flink by apache.

the class GraphCreatingVisitor method preVisit.

@SuppressWarnings("deprecation")
@Override
public boolean preVisit(Operator<?> c) {
    // check if we have been here before
    if (this.con2node.containsKey(c)) {
        return false;
    }
    final OptimizerNode n;
    // create a node for the operator (or sink or source) if we have not been here before
    if (c instanceof GenericDataSinkBase) {
        DataSinkNode dsn = new DataSinkNode((GenericDataSinkBase<?>) c);
        this.sinks.add(dsn);
        n = dsn;
    } else if (c instanceof GenericDataSourceBase) {
        n = new DataSourceNode((GenericDataSourceBase<?, ?>) c);
    } else if (c instanceof MapOperatorBase) {
        n = new MapNode((MapOperatorBase<?, ?, ?>) c);
    } else if (c instanceof MapPartitionOperatorBase) {
        n = new MapPartitionNode((MapPartitionOperatorBase<?, ?, ?>) c);
    } else if (c instanceof FlatMapOperatorBase) {
        n = new FlatMapNode((FlatMapOperatorBase<?, ?, ?>) c);
    } else if (c instanceof FilterOperatorBase) {
        n = new FilterNode((FilterOperatorBase<?, ?>) c);
    } else if (c instanceof ReduceOperatorBase) {
        n = new ReduceNode((ReduceOperatorBase<?, ?>) c);
    } else if (c instanceof GroupCombineOperatorBase) {
        n = new GroupCombineNode((GroupCombineOperatorBase<?, ?, ?>) c);
    } else if (c instanceof GroupReduceOperatorBase) {
        n = new GroupReduceNode((GroupReduceOperatorBase<?, ?, ?>) c);
    } else if (c instanceof InnerJoinOperatorBase) {
        n = new JoinNode((InnerJoinOperatorBase<?, ?, ?, ?>) c);
    } else if (c instanceof OuterJoinOperatorBase) {
        n = new OuterJoinNode((OuterJoinOperatorBase<?, ?, ?, ?>) c);
    } else if (c instanceof CoGroupOperatorBase) {
        n = new CoGroupNode((CoGroupOperatorBase<?, ?, ?, ?>) c);
    } else if (c instanceof CoGroupRawOperatorBase) {
        n = new CoGroupRawNode((CoGroupRawOperatorBase<?, ?, ?, ?>) c);
    } else if (c instanceof CrossOperatorBase) {
        n = new CrossNode((CrossOperatorBase<?, ?, ?, ?>) c);
    } else if (c instanceof BulkIterationBase) {
        n = new BulkIterationNode((BulkIterationBase<?>) c);
    } else if (c instanceof DeltaIterationBase) {
        n = new WorksetIterationNode((DeltaIterationBase<?, ?>) c);
    } else if (c instanceof Union) {
        n = new BinaryUnionNode((Union<?>) c);
    } else if (c instanceof PartitionOperatorBase) {
        n = new PartitionNode((PartitionOperatorBase<?>) c);
    } else if (c instanceof SortPartitionOperatorBase) {
        n = new SortPartitionNode((SortPartitionOperatorBase<?>) c);
    } else if (c instanceof BulkIterationBase.PartialSolutionPlaceHolder) {
        if (this.parent == null) {
            throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
        }
        final BulkIterationBase.PartialSolutionPlaceHolder<?> holder = (BulkIterationBase.PartialSolutionPlaceHolder<?>) c;
        final BulkIterationBase<?> enclosingIteration = holder.getContainingBulkIteration();
        final BulkIterationNode containingIterationNode = (BulkIterationNode) this.parent.con2node.get(enclosingIteration);
        // catch this for the recursive translation of step functions
        BulkPartialSolutionNode p = new BulkPartialSolutionNode(holder, containingIterationNode);
        p.setParallelism(containingIterationNode.getParallelism());
        n = p;
    } else if (c instanceof DeltaIterationBase.WorksetPlaceHolder) {
        if (this.parent == null) {
            throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
        }
        final DeltaIterationBase.WorksetPlaceHolder<?> holder = (DeltaIterationBase.WorksetPlaceHolder<?>) c;
        final DeltaIterationBase<?, ?> enclosingIteration = holder.getContainingWorksetIteration();
        final WorksetIterationNode containingIterationNode = (WorksetIterationNode) this.parent.con2node.get(enclosingIteration);
        // catch this for the recursive translation of step functions
        WorksetNode p = new WorksetNode(holder, containingIterationNode);
        p.setParallelism(containingIterationNode.getParallelism());
        n = p;
    } else if (c instanceof DeltaIterationBase.SolutionSetPlaceHolder) {
        if (this.parent == null) {
            throw new InvalidProgramException("It is currently not supported to create data sinks inside iterations.");
        }
        final DeltaIterationBase.SolutionSetPlaceHolder<?> holder = (DeltaIterationBase.SolutionSetPlaceHolder<?>) c;
        final DeltaIterationBase<?, ?> enclosingIteration = holder.getContainingWorksetIteration();
        final WorksetIterationNode containingIterationNode = (WorksetIterationNode) this.parent.con2node.get(enclosingIteration);
        // catch this for the recursive translation of step functions
        SolutionSetNode p = new SolutionSetNode(holder, containingIterationNode);
        p.setParallelism(containingIterationNode.getParallelism());
        n = p;
    } else {
        throw new IllegalArgumentException("Unknown operator type: " + c);
    }
    this.con2node.put(c, n);
    // key-less reducer (all-reduce)
    if (n.getParallelism() < 1) {
        // set the parallelism
        int par = c.getParallelism();
        if (par > 0) {
            if (this.forceParallelism && par != this.defaultParallelism) {
                par = this.defaultParallelism;
                Optimizer.LOG.warn("The parallelism of nested dataflows (such as step functions in iterations) is " + "currently fixed to the parallelism of the surrounding operator (the iteration).");
            }
        } else {
            par = this.defaultParallelism;
        }
        n.setParallelism(par);
    }
    return true;
}